Author

Andy Kim

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Frontier Curriculum and Adaptive Test-Time Compute for Efficient RLOO

It is asked whether a single success-probability signal can allocate compute more efficiently in both phases on Countdown with Qwen2.5-0.5B.

Marco Vizcarra, Andy Kim · 0 citations

Preprint Jul 2026

ToxScreen: Detecting Whether an LLM Has Been Poisoned

No method reliably surfaces every backdoor, but a broadly jailbreakable model is itself anomalous, a useful signal even when the exact trigger is not recovered, allowing defenders to filter jailbreaks.

A. Hughes, N. Xing, Collin Francel et al. · 0 citations